Future forecast: predicting malfunctions

Paul Boughton

How a prognostic tool helps forestall malfunctions and increase remaining useful life of power stations. By Moritz von Plate

Making remaining useful life (RUL) transparent and – ideally – actively controlling it, was the goal of deploying a prognostic solution in a hydro power station belonging to the Swiss utility company BKW Energie. In addition to the active management of RUL, maintenance scheduling and preparation were also to be optimised to lower the operation and maintenance costs. Additionally, the Swiss utility hoped to change the operational strategy of the plant in such a way that its operation during its RUL and the purchase planning for spare parts could be optimised.

In Switzerland power generation is currently focused on hydroelectric and nuclear sources. With an annual power production of about 146.7GWh, BKW is one of Europe's largest energy utilities. Some of the firm’s hydro electric power plants will be reaching the end of their originally planned life in the coming years. To determine the RUL of the plants and their key components such as bulb turbines, generators and transformers, to control and to extend their life and to determine the optimal renewal time for these components, the hydroelectric power plant (HPP) Bannwil implemented Cassantec’s automated prognostic solution in April 2014.

The RUL of the entire system can be influenced by the operating strategy since the respective RUL is highly dependent on the chosen workload of the individual components. Moreover, the prognostic solution supports and complements condition monitoring and diagnostics during regular operation of the system and thus the optimisation of maintenance planning, scope and costs.

Project execution

First of all, Cassantec collaborated with BKW to choose the most important components of the HPP Bannwil. Then Cassantec generated a prognostic report for the respective components based on current and historical condition and process data. These include, in particular, data on temperature, lubricants, vibrations, rotation speed and electrical data, which is recorded and stored during plant operation.

A computerised stochastic model analyses, aggregates and correlates this data with malfunction modes or life limiting factors. The resulting RUL distributions can be aggregated at plant level and updated (for example, daily, weekly, or monthly) in the desired time intervals. Cassantec presents the prognostic reports for the plant and all individual components in a secure online portal. BKW provides the current data needed for the update via a SharePoint server.

Based on existing data and the complementary know-how of BKW and Cassantec, prognostic reports are developed for all the abovementioned components. It turned out that the HPP Bannwil’s RUL was largely determined or limited by the generator in the third power plant unit. The main reason for this is a progressing defect that can be seen in the increased levels of the vibration parameters for this generator. Based on these parameters it can be seen how the generator RUL is dependent on the respective load scenario. With an operating strategy that limits the power of the generator to 7.6 MW and (if necessary) increases the power of the other two generators, constant bearing vibration gradients and correspondingly extended RUL are to be expected. With the appropriate adjustment of the HPP’s operating strategy, BKW can extend the RUL of the entire system.

Improve management today and tomorrow

As David Rhyner, asset manager of BKW, sums up: “The prognostic reports have improved our daily plant management and long-term planning. We can see what effect our decisions today will have on the entire plant operation. Thereby we expect to reduce our costs and to improve today the reliability of tomorrow.”

In the future BKW will receive a monthly update of the prognostic reports in Bannwil. Moreover, the solution is currently being rolled out to other hydro-electric power plants.

Prognostic power

Cassantec provides condition-based prognostic solutions for industrial asset management, using an innovative technology. The Cassantec Prognostic Report enables asset operators to understand when in the future a malfunction is likely to occur. The key benefits of the report are: informed condition-based maintenance planning; foresight and minimisation of asset downtime; and improved commercial strategies and reputation.

The accuracy of the solution has been confirmed via retrospective analysis. 99% of malfunctions were accurately predicted, with a horizon of up to five years. This accuracy even increases over time through machine learning.

Cassantec’s customers rely on the prognostic report to help eliminate critical asset-performance and process problems that remain unsolved by traditional data-collection, alarming, and (diagnostic) analysis tools. 

Moritz von Plate is CEO of Cassantec